{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4821960926055908, "min": 0.4821960926055908, "max": 1.4610344171524048, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14458.16796875, "min": 14458.16796875, "max": 44321.94140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989997.0, "min": 29902.0, "max": 989997.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989997.0, "min": 29902.0, "max": 989997.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.20713049173355103, "min": -0.11349965631961823, "max": 0.2651587426662445, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 51.98975372314453, "min": -27.353416442871094, "max": 67.3503189086914, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015605310909450054, "min": 0.00957944430410862, "max": 0.2760006785392761, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.916933059692383, "min": 2.4331789016723633, "max": 66.51616668701172, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06743754203281631, "min": 0.06488056533275523, "max": 0.07188568153681868, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9441255884594283, "min": 0.49688211541412797, "max": 1.0782852230522801, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.008965458461413316, "min": 0.00010325661821864333, "max": 0.008965458461413316, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.12551641845978642, "min": 0.0014455926550610066, "max": 0.12678100845247778, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.283711857842854e-06, "min": 7.283711857842854e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010197196600979996, "min": 0.00010197196600979996, "max": 0.0033818114727296, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242787142857145, "min": 0.10242787142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339902000000002, "min": 1.3886848, "max": 2.5272704000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025254435571428566, "min": 0.00025254435571428566, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035356209799999993, "min": 0.0035356209799999993, "max": 0.11275431295999996, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012784698978066444, "min": 0.012784698978066444, "max": 0.37784814834594727, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17898578941822052, "min": 0.17898578941822052, "max": 2.644937038421631, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 642.3111111111111, "min": 585.4166666666666, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28904.0, "min": 16829.0, "max": 33109.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7797732944289844, "min": -0.9999500517733395, "max": 1.0394874645086627, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 35.089798249304295, "min": -31.998401656746864, "max": 49.895398296415806, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7797732944289844, "min": -0.9999500517733395, "max": 1.0394874645086627, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 35.089798249304295, "min": -31.998401656746864, "max": 49.895398296415806, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08477925706279671, "min": 0.08110943076159553, "max": 7.574105474002221, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.815066567825852, "min": 3.815066567825852, "max": 128.75979305803776, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1742292642", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742294907" }, "total": 2265.311888797, "count": 1, "self": 0.5394317079999382, "children": { "run_training.setup": { "total": 0.033599447000028704, "count": 1, "self": 0.033599447000028704 }, "TrainerController.start_learning": { "total": 2264.738857642, "count": 1, "self": 1.4932787559678218, "children": { "TrainerController._reset_env": { "total": 3.3142388060000485, "count": 1, "self": 3.3142388060000485 }, "TrainerController.advance": { "total": 2259.845075928032, "count": 63319, "self": 1.492443753058069, "children": { "env_step": { "total": 1575.9980551269869, "count": 63319, "self": 1416.7328711509897, "children": { "SubprocessEnvManager._take_step": { "total": 158.45153975201788, "count": 63319, "self": 4.707585359092491, "children": { "TorchPolicy.evaluate": { "total": 153.7439543929254, "count": 62557, "self": 153.7439543929254 } } }, "workers": { "total": 0.8136442239792814, "count": 63319, "self": 0.0, "children": { "worker_root": { "total": 2259.424258101957, "count": 63319, "is_parallel": true, "self": 958.7407229339728, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005239703999905032, "count": 1, "is_parallel": true, "self": 0.003853166999988389, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013865369999166433, "count": 8, "is_parallel": true, "self": 0.0013865369999166433 } } }, "UnityEnvironment.step": { "total": 0.04928144899997733, "count": 1, "is_parallel": true, "self": 0.0005385800000112795, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048073199991449655, "count": 1, "is_parallel": true, "self": 0.00048073199991449655 }, "communicator.exchange": { "total": 0.04652187600004254, "count": 1, "is_parallel": true, "self": 0.04652187600004254 }, "steps_from_proto": { "total": 0.0017402610000090135, "count": 1, "is_parallel": true, "self": 0.0005362209999475454, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012040400000614682, "count": 8, "is_parallel": true, "self": 0.0012040400000614682 } } } } } } }, "UnityEnvironment.step": { "total": 1300.6835351679842, "count": 63318, "is_parallel": true, "self": 32.21012554802746, "children": { "UnityEnvironment._generate_step_input": { "total": 23.230149043958363, "count": 63318, "is_parallel": true, "self": 23.230149043958363 }, "communicator.exchange": { "total": 1147.2683698760047, "count": 63318, "is_parallel": true, "self": 1147.2683698760047 }, "steps_from_proto": { "total": 97.9748906999937, "count": 63318, "is_parallel": true, "self": 20.10442630015234, "children": { "_process_rank_one_or_two_observation": { "total": 77.87046439984135, "count": 506544, "is_parallel": true, "self": 77.87046439984135 } } } } } } } } } } }, "trainer_advance": { "total": 682.3545770479872, "count": 63319, "self": 2.6609138270202948, "children": { "process_trajectory": { "total": 128.17760125497, "count": 63319, "self": 127.90970643496996, "children": { "RLTrainer._checkpoint": { "total": 0.2678948200000377, "count": 2, "self": 0.2678948200000377 } } }, "_update_policy": { "total": 551.5160619659969, "count": 446, "self": 304.1709550710194, "children": { "TorchPPOOptimizer.update": { "total": 247.34510689497745, "count": 22806, "self": 247.34510689497745 } } } } } } }, "trainer_threads": { "total": 1.0079997991851997e-06, "count": 1, "self": 1.0079997991851997e-06 }, "TrainerController._save_models": { "total": 0.08626314399998591, "count": 1, "self": 0.001570660999732354, "children": { "RLTrainer._checkpoint": { "total": 0.08469248300025356, "count": 1, "self": 0.08469248300025356 } } } } } } }